Systematic Associations Between Phenotypes and Environmental
Exposures: Benchmarking Exposomic Research
NHANES
if(exists("con")) {
dbDisconnect(con)
remove(list=ls())
}
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ stringr 1.4.0
## ✔ readr 2.1.2 ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(DBI)
library(ggsci)
library(DT)
library(ggrepel)
library(cowplot)
library(reactable)
library(gt)
library(broom)
ep_assoc_summary_across_models <- function(summary_stats, glanced_stats) {
summary_stats_wide <- summary_stats |> pivot_wider(names_from = "model_type", values_from = c("estimate", "std.error", "statistic", "p.value"))
summary_stats_wide <- summary_stats_wide |> mutate(estimate_diff = estimate_adjusted-estimate_unadjusted)
adj_vs_base <- glanced |> select(-c(adj.r2, df.residual, null.deviance, df.null, deviance)) |> pivot_wider(names_from=model_type, values_from = c("rsq", "nobs", "AIC", "BIC"))
adj_vs_base <- adj_vs_base |> mutate(rsq_adjusted_base_diff=rsq_adjusted-rsq_base, rsq_adjusted_diff = rsq_adjusted-rsq_unadjusted)
summary_stats_wide |> left_join(adj_vs_base, by=c("evarname", "pvarname", "exposure_table_name", "phenotype_table_name"))
}
remove_units_from_string <- function(vardesc) {
gsub("\\(.*\\)$","", vardesc)
}
con <- DBI::dbConnect(RSQLite::SQLite(), dbname='../db/pe_summary_stats.sqlite')
varnames <- tbl(con, "variable_names_epcf")
adjusted_meta <- tbl(con, "adjusted_meta")
unadjusted_meta <- tbl(con, "unadjusted_meta")
adjusted_meta <- adjusted_meta |> left_join(unadjusted_meta |> select(evarname, pvarname, expo_name, vartype, estimate, p.value) |> rename(estimate_unadjusted=estimate, p.value_unadjusted=p.value), by=c("evarname", "pvarname", "expo_name", "vartype"))
mvr2 <- tbl(con, 'mvr2') |> mutate(mv = mve_rsq-base_rsq)
pe <- tbl(con, "pe")
glanced <- tbl(con, "glanced")
variable_domain <- tbl(con, "variable_domain")
expos <- pe |> filter(term %like% 'expo%')
expos_wide <- ep_assoc_summary_across_models(expos, glanced)
expos_wide <- expos_wide |> left_join(varnames, by=c("evarname"="Variable.Name", "exposure_table_name"="Data.File.Name"))
expos_wide <- expos_wide |> left_join(varnames |> select(Variable.Name, Data.File.Name, Variable.Description, Data.File.Description),
by=c("pvarname"="Variable.Name", "phenotype_table_name"="Data.File.Name"))
expos_wide <- expos_wide |> select(-Use.Constraints) |> rename(e_data_file_desc=Data.File.Description.x, p_data_file_desc=Data.File.Description.y,
e_variable_description=Variable.Description.x,
p_variable_description=Variable.Description.y
)
expos_wide <- expos_wide |> collect()
#expos_wide_summary <- expos_wide |> filter(term == 'expo' | term == 'expo1') |> group_by(evarname, pvarname) |> summarize(mean_adjusted_base_r2_diff = mean(rsq_adjusted_base_diff), mean_unadjusted_r2_diff=mean(rsq_adjusted_diff), total_n = sum(nobs_adjusted)) |> ungroup()
expos_wide_summary <- expos_wide |> filter(term == 'expo' | term == 'expo1' | term == 'expo2') |> group_by(evarname, pvarname) |> summarize(mean_adjusted_base_r2_diff = mean(rsq_adjusted_base_diff), mean_unadjusted_r2_diff=mean(rsq_adjusted_diff), total_n = sum(nobs_adjusted)) |> ungroup()
## `summarise()` has grouped output by 'evarname'. You can override using the
## `.groups` argument.
adjusted_meta <- adjusted_meta |> collect() |> left_join(expos_wide_summary, by=c("evarname", "pvarname"))
p_variable_domain <- variable_domain |> filter(epcf == 'p') |> collect() |> group_by(Variable.Name) |> summarise(pvardesc=first(Variable.Description),pcategory=first(category),psubcategory=first(subcategory))
e_variable_domain <- variable_domain |> filter(epcf == 'e') |> collect() |> group_by(Variable.Name) |> summarise(evardesc=first(Variable.Description),ecategory=first(category),esubcategory=first(subcategory))
adjusted_meta <- adjusted_meta |> left_join(p_variable_domain, by=c("pvarname"="Variable.Name"))
adjusted_meta <- adjusted_meta |> left_join(e_variable_domain, by=c("evarname"="Variable.Name"))
expos_wide <- expos_wide |> left_join(p_variable_domain, by=c("pvarname"="Variable.Name"))
expos_wide <- expos_wide |> left_join(e_variable_domain, by=c("evarname"="Variable.Name"))
mvr2 <- mvr2 |> collect() |> left_join(p_variable_domain, by=c("pvarname"="Variable.Name"))
Number of unique exposures and phenotypes
num_e <- length(unique(adjusted_meta$evarname))
num_p <- length(unique(adjusted_meta$pvarname))
num_e
## [1] 859
num_p
## [1] 319
num_e * num_p
## [1] 274021
Number exposures and phenotypes and associations in X number of
surveys
#adjusted_meta <- adjusted_meta |> unnest(glanced) |> unnest(tidied)
n_obss <- sort(unique(adjusted_meta$nobs))
num_tests <- map_df(n_obss, function(n) {
n_e <- adjusted_meta |> filter(nobs == n) |> pull(evarname) |> unique() |> length()
n_p <- adjusted_meta |> filter(nobs == n) |> pull(pvarname) |> unique() |> length()
nn <- nrow(adjusted_meta |> filter(nobs == n))
tibble(n_expos=n_e, n_phenos=n_p, n_pxe=nn)
})
num_tests |> mutate(n_surveys=n_obss) |> gt()
| n_expos |
n_phenos |
n_pxe |
n_surveys |
| 853 |
319 |
58906 |
1 |
| 650 |
278 |
38251 |
2 |
| 519 |
241 |
21600 |
3 |
| 411 |
224 |
36138 |
4 |
| 319 |
216 |
9160 |
5 |
| 326 |
82 |
8794 |
6 |
| 217 |
75 |
1827 |
7 |
| 196 |
64 |
9423 |
8 |
| 38 |
60 |
1051 |
9 |
| 27 |
54 |
1573 |
10 |
Keep number of surveys is greater than 2
adjusted_meta_2 <- adjusted_meta |> filter(nobs >= 2)
n_evars <- length(unique(adjusted_meta_2$evarname))
n_pvars <- length(unique(adjusted_meta_2$pvarname))
Sample sizes within and across all surveys
sample_size_per_pair <- expos_wide |> filter(term == 'expo' | term== 'expo1') |> group_by(evarname, pvarname) |> summarize(total_n=sum(nobs_adjusted), n_surveys=n(), median_n=median(nobs_adjusted))
## `summarise()` has grouped output by 'evarname'. You can override using the
## `.groups` argument.
Summary of the summary stats
adjusted_meta_2 <- adjusted_meta_2 |> ungroup() |> mutate(pval_BY=p.adjust(p.value, method="BY"), pvalue_bonferroni=p.adjust(p.value, method="bonferroni"))
adjusted_meta_2 <- adjusted_meta_2 |> mutate(sig_levels = case_when(
pvalue_bonferroni < 0.05 ~ 'Bonf.<0.05',
pval_BY < 0.05 ~ 'BY<0.05',
TRUE ~ '> BY & Bonf.'
))
bonf_thresh <- 0.05/nrow(adjusted_meta_2)
quantile(adjusted_meta_2$p.value, probs=c(0.01, .05, .1, .2, .3, .4, .5, .6, .7, .8, .9, .95, .99), na.rm = T)
## 1% 5% 10% 20% 30% 40%
## 2.553508e-27 3.398496e-10 3.332952e-06 1.761850e-03 2.141903e-02 8.095805e-02
## 50% 60% 70% 80% 90% 95%
## 1.826276e-01 3.179099e-01 4.734236e-01 6.422462e-01 8.190745e-01 9.093611e-01
## 99%
## 9.816266e-01
quantile(adjusted_meta_2$estimate, probs=c(0.01, .05, .1, .2, .3, .4, .5, .6, .7, .8, .9, .95, .99), na.rm = T)
## 1% 5% 10% 20% 30% 40%
## -0.203919498 -0.075944258 -0.046650432 -0.023478563 -0.012016041 -0.003777513
## 50% 60% 70% 80% 90% 95%
## 0.003753614 0.011768619 0.021248856 0.033866834 0.057029843 0.090201321
## 99%
## 0.287943341
sum(adjusted_meta_2$pvalue_bonferroni < 0.05)/nrow(adjusted_meta_2)
## [1] 0.08294671
adjusted_meta_2 |> group_by(sig_levels) |> count()
## # A tibble: 3 × 2
## # Groups: sig_levels [3]
## sig_levels n
## <chr> <int>
## 1 > BY & Bonf. 105092
## 2 Bonf.<0.05 10602
## 3 BY<0.05 12123
adjusted_meta_2 |> filter(sig_levels == 'BY<0.05') |> arrange(-p.value) |> head()
## # A tibble: 6 × 39
## evarname pvarname term type estimate std.e…¹ stati…² p.value i.squ…³ h.squ…⁴
## <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 URXDMA LBXPLTSI over… summ… -0.0343 0.0101 -3.38 7.20e-4 0 1
## 2 DR2TZINC DXXRAFAT over… summ… -0.0340 0.0101 -3.38 7.20e-4 0 1
## 3 DR1TP182 DXXRLA over… summ… 0.0292 0.00863 3.38 7.20e-4 0 1
## 4 LBXV1D LBXSATSI over… summ… -0.00719 0.00213 -3.38 7.20e-4 91.5 11.8
## 5 DSQTFA DXDSTTOT over… summ… 0.0483 0.0143 3.38 7.20e-4 0 1
## 6 DR1TNIAC LBXSIR over… summ… 0.0273 0.00806 3.38 7.20e-4 19.0 1.23
## # … with 29 more variables: tau.squared <dbl>, tau.squared.se <dbl>,
## # cochran.qe <dbl>, p.value.cochran.qe <dbl>, cochran.qm <dbl>,
## # p.value.cochran.qm <dbl>, df.residual <int>, logLik <dbl>, deviance <dbl>,
## # AIC <dbl>, BIC <dbl>, AICc <dbl>, nobs <int>, vartype <chr>,
## # expo_name <chr>, estimate_unadjusted <dbl>, p.value_unadjusted <dbl>,
## # mean_adjusted_base_r2_diff <dbl>, mean_unadjusted_r2_diff <dbl>,
## # total_n <int>, pvardesc <chr>, pcategory <chr>, psubcategory <chr>, …
## # ℹ Use `colnames()` to see all variable names
adjusted_meta_2 |> group_by(sig_levels) |> summarize(r2_25=quantile(mean_adjusted_base_r2_diff, probs=.25, na.rm = T),
r2_50=quantile(mean_adjusted_base_r2_diff, probs=.5, na.rm = T),
r2_75=quantile(mean_adjusted_base_r2_diff, probs=.75, na.rm = T),
r2_100=max(mean_adjusted_base_r2_diff, na.rm = T))
## # A tibble: 3 × 5
## sig_levels r2_25 r2_50 r2_75 r2_100
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 > BY & Bonf. 0.000357 0.000763 0.00162 0.112
## 2 Bonf.<0.05 0.00225 0.00425 0.00842 0.547
## 3 BY<0.05 0.00114 0.00196 0.00371 0.0785
adjusted_meta_2 |> filter(sig_levels == 'Bonf.<0.05') |> arrange(-mean_adjusted_base_r2_diff)
## # A tibble: 10,602 × 39
## evarn…¹ pvarn…² term type estim…³ std.e…⁴ stati…⁵ p.value i.squ…⁶ h.squ…⁷
## <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 URXDHB URXUCR over… summ… 0.766 0.0191 40.1 0 0 1
## 2 URXPHG URXUCR over… summ… 0.673 0.0214 31.4 4.42e-216 0 1
## 3 URXUCS URXUCR over… summ… 0.647 0.0214 30.2 1.39e-200 0 1
## 4 URXMAD URXUCR over… summ… 0.662 0.0235 28.1 4.19e-174 0 1
## 5 URXMBP URXUCR over… summ… 0.642 0.0180 35.7 1.97e-279 0 1
## 6 URXUMO URXUCR over… summ… 0.633 0.0184 34.3 3.01e-258 0 1
## 7 LBXOTT LBXSTR over… summ… 0.633 0.0391 16.2 7.28e- 59 39.9 1.66
## 8 LBXOTT LBXTR over… summ… 0.631 0.0392 16.1 3.09e- 58 38.2 1.62
## 9 URXMIB URXUCR over… summ… 0.602 0.0202 29.9 3.58e-196 0 1
## 10 URXUTL URXUCR over… summ… 0.585 0.0158 36.9 8.25e-299 0 1
## # … with 10,592 more rows, 29 more variables: tau.squared <dbl>,
## # tau.squared.se <dbl>, cochran.qe <dbl>, p.value.cochran.qe <dbl>,
## # cochran.qm <dbl>, p.value.cochran.qm <dbl>, df.residual <int>,
## # logLik <dbl>, deviance <dbl>, AIC <dbl>, BIC <dbl>, AICc <dbl>, nobs <int>,
## # vartype <chr>, expo_name <chr>, estimate_unadjusted <dbl>,
## # p.value_unadjusted <dbl>, mean_adjusted_base_r2_diff <dbl>,
## # mean_unadjusted_r2_diff <dbl>, total_n <int>, pvardesc <chr>, …
## # ℹ Use `print(n = ...)` to see more rows, and `colnames()` to see all variable names
## qqplot
pval_qq <- data.frame(observed = sort(adjusted_meta_2$p.value), expected = (1:nrow(adjusted_meta_2))/nrow(adjusted_meta_2))
qq_p <- ggplot(pval_qq, aes(-log10(expected), -log10(observed)))
qq_p <- qq_p + geom_point()
##
p <- ggplot(pval_qq, aes(observed))
p <- p + geom_histogram(bins=100) + theme_bw()
p <- p + geom_hline(yintercept = 1, color='blue')
p <- p + xlab("P-E association pvalue")
p_hist <- p
p_hist

p <- ggplot(pval_qq |> filter(observed < 1e-3), aes(-log10(observed)))
p <- p + geom_histogram(bins=200) + theme_bw() + scale_x_continuous(limits=c(0, 100))
p <- p + geom_hline(yintercept = 1, color='blue')
p <- p + xlab("P-E association pvalue")
p_hist <- p
p_hist
## Warning: Removed 122 rows containing non-finite values (stat_bin).
## Warning: Removed 2 rows containing missing values (geom_bar).

p <- ggplot(adjusted_meta_2, aes(p.value))
p <- p + geom_density() + theme_bw() + facet_grid(~ecategory)
p1 <- p + xlab("P-E association pvalue")
p <- ggplot(adjusted_meta_2, aes(p.value))
p <- p + geom_density() + theme_bw() + facet_grid(~pcategory)
p2 <- p + xlab("P-E association pvalue")
plot_grid(p1, p2, nrow=2, labels=c("A", "B"))

zoom in the distribution
p_plot <- adjusted_meta_2 |> select(ecategory, pcategory, p.value)
p <- ggplot(p_plot,aes(p.value))
p <- p + geom_histogram(aes(y=..density..)) + geom_density() + theme_bw() + facet_grid(~ecategory)
p1 <- p + xlab("P-E association pvalue")
p <- ggplot(p_plot, aes(p.value))
p <- p + geom_histogram(aes(y=..density..)) + geom_density() + theme_bw() + facet_grid(~pcategory)
p2 <- p + xlab("P-E association pvalue")
plot_grid(p1, p2, nrow=2, labels=c("A", "B"))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Association Size vs. -log10(pvalue)
e_summary <- adjusted_meta_2 |> group_by(evarname) |> arrange(pvalue_bonferroni) |>
summarize(mean_r2=mean(mean_adjusted_base_r2_diff, na.rm=T), mean_estimate=mean(abs(estimate), na.rm=T),
median_pvalue=median(p.value, na.rm=T), n_sig=sum(pvalue_bonferroni < 0.05, na.rm=T),
n_tests=sum(!is.na(pvalue_bonferroni)), median_i.squared=median(i.squared, na.rm=T),
max_r2=first(mean_adjusted_base_r2_diff), max_pvarname=first(pvarname) , max_estimate=first(estimate), max_p.value=first(p.value)) |> mutate(n_sig_pct=n_sig/n_tests)
p_summary <- adjusted_meta_2 |> group_by(pvarname) |> arrange(pvalue_bonferroni) |>
summarize(mean_r2=mean(mean_adjusted_base_r2_diff, na.rm=T), mean_estimate=mean(abs(estimate), na.rm=T),
median_pvalue=median(p.value, na.rm=T), n_sig=sum(pvalue_bonferroni < 0.05, na.rm=T),
n_tests=sum(!is.na(pvalue_bonferroni)), median_i.squared=median(i.squared, na.rm=T),
max_r2=first(mean_adjusted_base_r2_diff), max_evarname=first(evarname) , max_estimate=first(estimate), max_p.value=first(p.value)) |> mutate(n_sig_pct=n_sig/n_tests)
## deeper summary by group
p_group_summary <- adjusted_meta_2 |> unite(p_scategory, c(pcategory, psubcategory)) |> group_by(p_scategory) |> arrange(pvalue_bonferroni) |>
summarize(mean_r2=mean(mean_adjusted_base_r2_diff, na.rm=T), mean_estimate=mean(abs(estimate), na.rm=T),
median_pvalue=median(p.value, na.rm=T), n_sig=sum(pvalue_bonferroni < 0.05, na.rm=T),
n_tests=sum(!is.na(pvalue_bonferroni)), median_i.squared=median(i.squared, na.rm=T),
max_r2=first(mean_adjusted_base_r2_diff), max_evarname=first(evarname) , max_estimate=first(estimate), max_p.value=first(p.value)) |> mutate(n_sig_pct=n_sig/n_tests)
e_group_summary <- adjusted_meta_2 |> unite(e_scategory, c(ecategory, esubcategory)) |> group_by(e_scategory) |> arrange(pvalue_bonferroni) |>
summarize(mean_r2=mean(mean_adjusted_base_r2_diff, na.rm=T),
mean_abs_estimate=mean(abs(estimate), na.rm=T),
mean_estimate=mean((estimate), na.rm=T),
median_pvalue=median(p.value, na.rm=T),
n_sig=sum(pvalue_bonferroni < 0.05, na.rm=T),
n_tests=sum(!is.na(pvalue_bonferroni)),
median_i.squared=median(i.squared, na.rm=T),
max_r2=first(mean_adjusted_base_r2_diff),
max_pvarname=first(pvarname),
max_estimate=first(estimate), max_p.value=first(p.value)) |> mutate(n_sig_pct=n_sig/n_tests)
Tables 1 and 2
##
e_group_summary <- adjusted_meta_2 |> filter(expo_name %in% c('expo', 'expo1', 'expo2', 'expo3')) |> filter(mean_adjusted_base_r2_diff <= .1) |> unite(e_scategory, c(ecategory, esubcategory)) |> group_by(e_scategory) |> arrange(pvalue_bonferroni,mean_adjusted_base_r2_diff) |>
summarize(
#median_r2=mean(mean_adjusted_base_r2_diff, na.rm=T),
#median_abs_estimate=median(abs(estimate), na.rm=T),
n_sig=sum(pvalue_bonferroni < 0.05, na.rm=T),
n_tests=sum(!is.na(pvalue_bonferroni)),
#median_i.squared=median(i.squared, na.rm=T),
max_r2=first(mean_adjusted_base_r2_diff),
max_termname=remove_units_from_string(first(expo_name)),
max_pvarname=remove_units_from_string(first(pvardesc)),
max_evarname=remove_units_from_string(first(evardesc)),
max_estimate=first(estimate), max_p.value=first(p.value), max_i.squared=first(i.squared)) |> mutate(n_sig_pct=n_sig/n_tests)
e_bonf_group_summary <- adjusted_meta_2 |> filter(sig_levels == 'Bonf.<0.05') |>
unite(e_scategory, c(ecategory, esubcategory)) |>
mutate(sgn=ifelse(sign(estimate) <0, 'neg', 'pos')) |> group_by(e_scategory, sgn) |> arrange(pvalue_bonferroni) |>
summarize(median_bonf_r2=median(mean_adjusted_base_r2_diff, na.rm=T),
q25_bonf_estimate=quantile(estimate, probs=.25, na.rm=T),
median_bonf_estimate=median((estimate), na.rm=T),
q75_bonf_estimate=quantile(estimate, probs=.75, na.rm=T)
)
## `summarise()` has grouped output by 'e_scategory'. You can override using the
## `.groups` argument.
e_bonf_group_summary <- e_bonf_group_summary |> pivot_wider(names_from=sgn, values_from=(c(median_bonf_r2, q25_bonf_estimate, median_bonf_estimate, q75_bonf_estimate)))
## merge
e_group_summary <- e_group_summary |> left_join(e_bonf_group_summary, by='e_scategory')
e_group_summary <- e_group_summary |> separate(col=e_scategory, into=c("escategory", "esubcategory"), sep="_")
e_group_summary <- e_group_summary |> filter(n_sig > 1)
e_group_summary <- e_group_summary |> select(escategory, esubcategory, n_tests, n_sig_pct, median_bonf_r2_neg, median_bonf_r2_pos, q25_bonf_estimate_neg, median_bonf_estimate_neg, q75_bonf_estimate_neg, q25_bonf_estimate_pos, median_bonf_estimate_pos, q75_bonf_estimate_pos,
max_pvarname, max_evarname, max_estimate, max_r2, max_p.value, max_i.squared)
e_group_summary<- e_group_summary |> gt() |>
fmt_number(columns = c(starts_with("q"), starts_with("med")), decimals = 3) |>
fmt_number(columns = c(max_r2, max_estimate), decimals = 3) |>
fmt_number(columns = c(n_sig_pct), decimals = 2) |>
fmt_number(columns = c(max_i.squared), decimals = 0) |>
fmt_scientific(columns = max_p.value, decimals = 0)
e_group_summary <- e_group_summary |>
tab_spanner(label = "Effect Sizes < 0",columns = ends_with("neg")) |>
tab_spanner(label = "Effect Sizes > 0",columns = ends_with("pos"))
e_group_summary <- e_group_summary |>
tab_spanner(label = "Example P-E Association (lowest p.value for E domain)",columns = starts_with("max"))
e_group_summary |> gtsave('./e_group_summary.html')
e_group_summary
| escategory |
esubcategory |
n_tests |
n_sig_pct |
Effect Sizes < 0
|
Effect Sizes > 0
|
Example P-E Association (lowest p.value for E domain)
|
| median_bonf_r2_neg |
q25_bonf_estimate_neg |
median_bonf_estimate_neg |
q75_bonf_estimate_neg |
median_bonf_r2_pos |
q25_bonf_estimate_pos |
median_bonf_estimate_pos |
q75_bonf_estimate_pos |
max_pvarname |
max_evarname |
max_estimate |
max_r2 |
max_p.value |
max_i.squared |
| allergy |
NA |
464 |
0.01 |
NA |
NA |
NA |
NA |
0.001 |
0.321 |
0.331 |
0.650 |
Ward's triangle bone mineral content |
Tissue transglutaminase |
0.650 |
0.002 |
1 × 10−10 |
0 |
| housing |
NA |
556 |
0.01 |
0.001 |
−0.603 |
−0.472 |
−0.258 |
0.001 |
0.174 |
0.275 |
0.384 |
Alkaline phosphotase |
Is this {mobile home/house/apartment} owned, being bought, rented, or occup |
−0.103 |
0.002 |
3 × 10−17 |
27 |
| income |
NA |
513 |
0.01 |
0.005 |
−0.464 |
−0.421 |
−0.390 |
0.007 |
0.203 |
0.211 |
0.218 |
Left Arm Total |
Do {you/NAMES OF OTHER FAMILY/you and NAMES OF FAMILY MEMBERS} have more th |
0.194 |
0.006 |
5 × 10−8 |
0 |
| infection |
NA |
7015 |
0.04 |
0.002 |
−1.007 |
−0.450 |
−0.196 |
0.002 |
0.115 |
0.239 |
0.514 |
Subtotal Lean excl BMC |
Hepatitis D |
0.660 |
0.000 |
2 × 10−86 |
0 |
| nutrients |
dietary biomarker |
8301 |
0.16 |
0.010 |
−0.153 |
−0.104 |
−0.076 |
0.009 |
0.078 |
0.105 |
0.169 |
Total cholesterol |
g-tocopherol |
0.263 |
0.064 |
1 × 10−233 |
0 |
| nutrients |
dietary interview |
37852 |
0.12 |
0.004 |
−0.076 |
−0.061 |
−0.049 |
0.002 |
0.041 |
0.048 |
0.060 |
Direct HDL-Cholesterol |
Alcohol |
0.201 |
0.037 |
3 × 10−145 |
0 |
| nutrients |
supplements |
14619 |
0.01 |
0.004 |
−0.120 |
−0.076 |
−0.057 |
0.012 |
0.086 |
0.117 |
0.144 |
RBC folate |
Any Dietary Supplements taken in the past 24 hour? |
−0.511 |
0.050 |
2 × 10−178 |
0 |
| physical activity |
NA |
4126 |
0.18 |
0.005 |
−0.105 |
−0.068 |
−0.054 |
0.004 |
0.049 |
0.064 |
0.096 |
Left Leg Percent Fat |
Vigorous Leisure Per Week |
−0.155 |
0.020 |
5 × 10−91 |
2 |
| pollutant |
amide |
456 |
0.22 |
0.012 |
−0.138 |
−0.112 |
−0.081 |
0.005 |
0.064 |
0.078 |
0.108 |
White blood cell count |
Acrylamide |
0.142 |
0.018 |
4 × 10−45 |
0 |
| pollutant |
amine |
1233 |
0.05 |
0.007 |
−0.106 |
−0.086 |
−0.082 |
0.013 |
0.098 |
0.116 |
0.162 |
Creatinine, urine |
4-Aminobiphenyl, urine |
0.322 |
0.095 |
3 × 10−104 |
0 |
| pollutant |
deet |
712 |
0.00 |
0.003 |
−0.054 |
−0.054 |
−0.054 |
0.006 |
0.074 |
0.074 |
0.074 |
Uric acid |
DEET acid |
0.074 |
0.006 |
4 × 10−8 |
0 |
| pollutant |
diakyl |
2285 |
0.05 |
0.002 |
−0.066 |
−0.042 |
−0.021 |
0.004 |
0.053 |
0.063 |
0.077 |
Blood urea nitrogen |
Urinary Perchlorate |
0.126 |
0.016 |
4 × 10−74 |
1 |
| pollutant |
heavy metals |
7450 |
0.11 |
0.006 |
−0.108 |
−0.086 |
−0.067 |
0.006 |
0.066 |
0.081 |
0.097 |
Waist Circumference |
Lead |
−0.164 |
0.018 |
2 × 10−174 |
0 |
| pollutant |
hydrocarbon |
2388 |
0.11 |
0.008 |
−0.116 |
−0.091 |
−0.074 |
0.007 |
0.071 |
0.089 |
0.105 |
White blood cell count |
2-fluorene |
0.172 |
0.028 |
1 × 10−57 |
6 |
| pollutant |
organochlorine |
5231 |
0.04 |
0.030 |
−0.345 |
−0.264 |
−0.151 |
0.022 |
0.131 |
0.181 |
0.271 |
Arm Circumference |
PCB194 |
−0.374 |
0.050 |
1 × 10−45 |
0 |
| pollutant |
organophosphate |
472 |
0.04 |
0.000 |
−0.034 |
−0.018 |
−0.014 |
0.000 |
0.011 |
0.011 |
0.012 |
Segmented neutrophils percent |
Dimethoate |
−0.028 |
0.000 |
3 × 10−94 |
0 |
| pollutant |
phenols |
2887 |
0.03 |
0.004 |
−0.073 |
−0.065 |
−0.057 |
0.006 |
0.066 |
0.082 |
0.093 |
Body Mass Index |
Ethyl paraben |
−0.110 |
0.012 |
5 × 10−36 |
0 |
| pollutant |
phthalates |
4390 |
0.11 |
0.007 |
−0.095 |
−0.081 |
−0.068 |
0.008 |
0.068 |
0.085 |
0.100 |
Osmolality |
Mono- |
0.142 |
0.019 |
4 × 10−54 |
0 |
| pollutant |
polyfluoro |
3111 |
0.06 |
0.010 |
−0.130 |
−0.106 |
−0.078 |
0.012 |
0.091 |
0.115 |
0.158 |
Albumin |
Perfluorohexane sulfonic acid |
0.157 |
0.023 |
9 × 10−40 |
6 |
| pollutant |
priority pesticide |
2574 |
0.03 |
0.000 |
−0.024 |
−0.014 |
−0.011 |
0.001 |
0.013 |
0.034 |
0.078 |
Arm Circumference |
2,4,5-T (ug/L) result |
−0.026 |
0.001 |
2 × 10−249 |
0 |
| pollutant |
VOC |
12975 |
0.06 |
0.006 |
−0.095 |
−0.079 |
−0.050 |
0.007 |
0.056 |
0.080 |
0.109 |
Baseline 1st Test Spirometry, Forced Vital Capacity, in mL. |
Blood Carbon Tetrachloride Result |
−0.015 |
0.000 |
1 × 10−96 |
0 |
| smoking |
smoking behavior |
2717 |
0.04 |
0.007 |
−0.254 |
−0.205 |
−0.150 |
0.008 |
0.106 |
0.162 |
0.277 |
Mean cell volume |
Smoking: current, ever, never |
0.474 |
0.031 |
2 × 10−194 |
21 |
| smoking |
smoking biomarker |
1393 |
0.11 |
0.004 |
−0.088 |
−0.072 |
−0.057 |
0.010 |
0.065 |
0.108 |
0.162 |
Segmented neutrophils num |
Cotinine |
0.165 |
0.023 |
6 × 10−211 |
0 |
##
p_group_summary <- adjusted_meta_2 |> filter(expo_name %in% c('expo', 'expo1', 'expo2', 'expo3')) |> filter(mean_adjusted_base_r2_diff <= .1) |> unite(p_scategory, c(pcategory, psubcategory)) |> group_by(p_scategory) |> arrange(pvalue_bonferroni,mean_adjusted_base_r2_diff) |>
summarize(
#median_r2=mean(mean_adjusted_base_r2_diff, na.rm=T),
#median_abs_estimate=median(abs(estimate), na.rm=T),
n_sig=sum(pvalue_bonferroni < 0.05, na.rm=T),
n_tests=sum(!is.na(pvalue_bonferroni)),
#median_i.squared=median(i.squared, na.rm=T),
max_r2=first(mean_adjusted_base_r2_diff),
max_termname=remove_units_from_string(first(expo_name)),
max_pvarname=remove_units_from_string(first(pvardesc)),
max_evarname=remove_units_from_string(first(evardesc)),
max_estimate=first(estimate), max_p.value=first(p.value), max_i.squared=first(i.squared)) |> mutate(n_sig_pct=n_sig/n_tests)
p_bonf_group_summary <- adjusted_meta_2 |> filter(sig_levels == 'Bonf.<0.05') |>
unite(p_scategory, c(pcategory, psubcategory)) |>
mutate(sgn=ifelse(sign(estimate) <0, 'neg', 'pos')) |> group_by(p_scategory, sgn) |> arrange(pvalue_bonferroni) |>
summarize(median_bonf_r2=median(mean_adjusted_base_r2_diff, na.rm=T),
q25_bonf_estimate=quantile(estimate, probs=.25, na.rm=T),
median_bonf_estimate=median((estimate), na.rm=T),
q75_bonf_estimate=quantile(estimate, probs=.75, na.rm=T)
)
## `summarise()` has grouped output by 'p_scategory'. You can override using the
## `.groups` argument.
p_bonf_group_summary <- p_bonf_group_summary |> pivot_wider(names_from=sgn, values_from=(c(median_bonf_r2, q25_bonf_estimate, median_bonf_estimate, q75_bonf_estimate)))
## merge
p_group_summary <- p_group_summary |> left_join(p_bonf_group_summary, by='p_scategory')
p_group_summary <- p_group_summary |> separate(col=p_scategory, into=c("pscategory", "psubcategory"), sep="_")
p_group_summary <- p_group_summary |> filter(n_sig > 1)
p_group_summary <- p_group_summary |> select(pscategory, psubcategory, n_tests, n_sig_pct, q25_bonf_estimate_neg, median_bonf_estimate_neg, q75_bonf_estimate_neg, q25_bonf_estimate_pos, median_bonf_estimate_pos, q75_bonf_estimate_pos,
max_pvarname, max_evarname, max_estimate, max_r2, max_p.value, max_i.squared)
p_group_summary<- p_group_summary |> gt() |>
fmt_number(columns = c(starts_with("q"), starts_with("med")), decimals = 3) |>
fmt_number(columns = c(max_r2, max_estimate), decimals = 3) |>
fmt_number(columns = c(n_sig_pct), decimals = 2) |>
fmt_number(columns = c(max_i.squared), decimals = 0) |>
fmt_scientific(columns = max_p.value, decimals = 0)
p_group_summary <- p_group_summary |>
tab_spanner(label = "Effect Sizes < 0",columns = ends_with("neg")) |>
tab_spanner(label = "Effect Sizes > 0",columns = ends_with("pos"))
p_group_summary <- p_group_summary |>
tab_spanner(label = "Example P-E Association (lowest p.value for E domain)",columns = starts_with("max"))
p_group_summary |> gtsave('./p_group_summary.html')
p_group_summary
| pscategory |
psubcategory |
n_tests |
n_sig_pct |
Effect Sizes < 0
|
Effect Sizes > 0
|
Example P-E Association (lowest p.value for E domain)
|
| q25_bonf_estimate_neg |
median_bonf_estimate_neg |
q75_bonf_estimate_neg |
q25_bonf_estimate_pos |
median_bonf_estimate_pos |
q75_bonf_estimate_pos |
max_pvarname |
max_evarname |
max_estimate |
max_r2 |
max_p.value |
max_i.squared |
| aging |
NA |
362 |
0.01 |
NA |
NA |
NA |
0.183 |
0.310 |
0.437 |
Mean T/S ratio |
Platinum, urine |
0.056 |
0.002 |
7 × 10−20 |
6 |
| anthropometric |
dexa |
57728 |
0.09 |
−0.100 |
−0.076 |
−0.061 |
0.044 |
0.056 |
0.082 |
Android fat mass |
25-hydroxyvitamin D3 |
−0.217 |
0.036 |
3 × 10−133 |
0 |
| anthropometric |
NA |
6650 |
0.18 |
−0.121 |
−0.075 |
−0.050 |
0.041 |
0.060 |
0.088 |
Arm Circumference |
2,4,5-T (ug/L) result |
−0.026 |
0.001 |
2 × 10−249 |
0 |
| biochemistry |
bone |
1381 |
0.08 |
−0.081 |
−0.072 |
−0.041 |
0.045 |
0.066 |
0.099 |
Total calcium |
Retinol |
0.230 |
0.044 |
6 × 10−185 |
0 |
| biochemistry |
electrolyte |
3308 |
0.09 |
−0.093 |
−0.073 |
−0.059 |
0.053 |
0.089 |
0.112 |
Chloride |
Molybdenum, urine |
0.176 |
0.029 |
6 × 10−84 |
0 |
| biochemistry |
hormone |
4759 |
0.02 |
−0.107 |
−0.080 |
−0.071 |
0.049 |
0.078 |
0.105 |
Parathyroid Hormone(Elecys method) pg/mL |
Vitamin D |
−0.269 |
0.058 |
2 × 10−71 |
14 |
| biochemistry |
immunity |
662 |
0.10 |
−0.078 |
−0.059 |
−0.042 |
0.064 |
0.075 |
0.098 |
Globulin |
Metsulfuron methyl |
−0.028 |
0.001 |
6 × 10−51 |
0 |
| biochemistry |
inflammation |
708 |
0.09 |
−0.084 |
−0.064 |
−0.054 |
0.060 |
0.082 |
0.111 |
C-reactive protein |
cis-b-carotene |
−0.159 |
0.022 |
1 × 10−66 |
0 |
| biochemistry |
injury |
591 |
0.03 |
−0.074 |
−0.066 |
−0.051 |
0.050 |
0.060 |
0.080 |
Lactate dehydrogenase LDH |
Smoking: current, ever, never |
−0.169 |
0.004 |
8 × 10−42 |
0 |
| biochemistry |
kidney |
2897 |
0.17 |
−0.085 |
−0.060 |
−0.046 |
0.068 |
0.104 |
0.324 |
Uric acid |
Retinol |
0.207 |
0.034 |
1 × 10−157 |
19 |
| biochemistry |
lipids |
4039 |
0.06 |
−0.099 |
−0.069 |
−0.055 |
0.077 |
0.199 |
0.311 |
Total cholesterol |
g-tocopherol |
0.263 |
0.064 |
1 × 10−233 |
0 |
| biochemistry |
liver |
3170 |
0.06 |
−0.089 |
−0.063 |
−0.042 |
0.052 |
0.066 |
0.088 |
Alkaline phosphotase |
Pyridoxal 5'-phosphate |
−0.115 |
0.013 |
8 × 10−84 |
0 |
| biochemistry |
liver/kidney |
1994 |
0.10 |
−0.089 |
−0.068 |
−0.046 |
0.049 |
0.073 |
0.113 |
Albumin |
Pyridoxal 5'-phosphate |
0.252 |
0.060 |
1 × 10−84 |
52 |
| biochemistry |
metabolic |
3140 |
0.07 |
−0.106 |
−0.073 |
−0.052 |
0.072 |
0.127 |
0.174 |
Glycohemoglobin |
Nicosulfuron |
0.016 |
0.000 |
2 × 10−151 |
0 |
| biochemistry |
nutritional status |
5042 |
0.11 |
−0.116 |
−0.091 |
−0.074 |
0.074 |
0.092 |
0.122 |
Folate, RBC |
Vitamin B12 |
0.245 |
0.057 |
7 × 10−200 |
0 |
| biochemistry |
psa |
1179 |
0.01 |
−0.088 |
−0.086 |
−0.072 |
0.153 |
0.153 |
0.153 |
Prostate specific antigen ratio |
Cadmium |
−0.086 |
0.007 |
3 × 10−9 |
0 |
| blood pressure |
NA |
2952 |
0.05 |
−0.096 |
−0.065 |
−0.045 |
0.061 |
0.079 |
0.104 |
60 sec. pulse (30 sec. pulse * 2): |
trans-b-carotene |
−0.144 |
0.018 |
1 × 10−67 |
0 |
| blood |
iron |
3549 |
0.04 |
−0.152 |
−0.109 |
−0.075 |
0.062 |
0.091 |
0.143 |
Iron, refigerated |
g-tocopherol |
−0.151 |
0.021 |
7 × 10−110 |
0 |
| blood |
NA |
12763 |
0.06 |
−0.080 |
−0.051 |
−0.039 |
0.064 |
0.095 |
0.129 |
Segmented neutrophils num |
Cotinine |
0.165 |
0.023 |
6 × 10−211 |
0 |
| fitness |
NA |
666 |
0.06 |
−0.124 |
−0.088 |
−0.069 |
0.090 |
0.113 |
0.129 |
Predicted maximal oxygen uptake |
g-tocopherol |
−0.156 |
0.023 |
5 × 10−76 |
0 |
| lung |
exhaled NO |
390 |
0.04 |
−0.196 |
−0.171 |
−0.140 |
0.211 |
0.373 |
0.536 |
Mean of two reproducible FENO measurements, in parts per billion |
Smoking: current, ever, never |
−0.524 |
0.040 |
2 × 10−86 |
0 |
| lung |
lung function |
782 |
0.09 |
−0.143 |
−0.069 |
−0.046 |
0.041 |
0.047 |
0.059 |
Baseline 1st Test Spirometry, Forced Vital Capacity, in mL. |
Blood Carbon Tetrachloride Result |
−0.015 |
0.000 |
1 × 10−96 |
0 |
| microbiome |
NA |
5520 |
0.01 |
−0.076 |
−0.070 |
−0.034 |
0.026 |
0.104 |
0.117 |
RSV_ObservedOTUsSD |
Herpes Simplex Virus II |
−1.065 |
0.001 |
4 × 10−29 |
0 |
adjusted_meta_2 <- adjusted_meta_2 |> mutate(p_cap = ifelse(p.value < 1e-30, 1e-30, p.value))
p <- ggplot(adjusted_meta_2 |> filter(ecategory != 'autoantibody'), aes(estimate, -log10(p_cap)))
p <- p + geom_point(shape='.') + scale_x_continuous(limits=c(-1, 1))
p <- p + facet_grid(ecategory ~ .) + scale_color_npg()
p <- p + geom_hline(yintercept = -log10(.05/nrow(adjusted_meta_2)), color='lightblue')
p <- p + theme_minimal() + theme(legend.position = "none") +ylab('p.value') + xlab("estimate")
p1 <- p
## uBiome only
p <- ggplot(adjusted_meta_2 |> filter(pcategory == 'microbiome'), aes(estimate, -log10(p_cap)))
p <- p + geom_point(shape='.') + scale_x_continuous(limits=c(-1, 1))
p <- p + facet_grid(ecategory ~ .) + scale_color_npg()
p <- p + geom_hline(yintercept = -log10(.05/nrow(adjusted_meta_2)), color='lightblue')
p <- p + theme_minimal() + theme(legend.position = "none") +ylab('p.value') + xlab("estimate")
p <- ggplot(adjusted_meta_2, aes(estimate, -log10(p_cap)))
p <- p + geom_point(shape='.') + scale_x_continuous(limits=c(-1, 1))
p <- p + facet_grid(pcategory ~ .) + scale_color_npg()
p <- p + geom_hline(yintercept = -log10(.05/nrow(adjusted_meta_2)), color='lightblue')
p <- p + theme_minimal() + theme(legend.position = "none") +ylab('p.value') + xlab("estimate")
p2 <-p
plot_grid(p1, p2, ncol=2, labels=c("A", "B"))
## Warning: Removed 73 rows containing missing values (geom_point).
## Removed 73 rows containing missing values (geom_point).

# library(circlize)
# # create circos plot visualizing 5 phenotype associations from adjusted_meta_2
# pvarnames_to_circos <- c("BMXBMI", "MSYSTOLIC","LBXGLU", "TeloMean", "LBXTC")
# pcircos <- adjusted_meta_2 |> filter(pvarname %in% pvarnames_to_circos) |> filter(vartype == 'continuous') |> select(c("evarname", "ecategory", "esubcategory", "evardesc", "pvarname", "pval_BY", "estimate"))
#
# pcircos <- pcircos |> unite(ecategory_sub, ecategory, esubcategory, sep="_")
#
# evarname_per_sub <- pcircos |> group_by(ecategory_sub, evarname) |> count() |> ungroup() |> select(-n)
# #m_per_ecategory <- uevarname_per_sub |> ungroup() |> select(-n) |> group_by(ecategory_sub) |> count()
#
# evarname_per_sub <- evarname_per_sub |> group_by(ecategory_sub) |> mutate(index = match(evarname, unique(evarname)))
# #m_per_ecategory <- m_per_ecategory |> filter(ecategory_sub != 'pollutant_pyrethoid',
# # ecategory_sub != 'allergy_NA',
# # ecategory_sub != 'pollutant_amide',
# # )
# pcircos_2 <- pcircos |> left_join(evarname_per_sub |> ungroup()) # this will give an index to each
# m_per_ecategory <- evarname_per_sub |> count()
#
# m_per_ecategory <- m_per_ecategory |> filter(n >= 10)
#
# xlims <- matrix(nrow=length(m_per_ecategory$ecategory_sub), data=0, ncol=1) |> cbind(matrix(nrow=length(m_per_ecategory$ecategory_sub), data=m_per_ecategory$n, ncol=1))
#
# #circos.par(cell.padding = c(0.02, 0, 0.02, 0))
# pcircos_3 <- pcircos_2 |> filter(ecategory_sub %in% m_per_ecategory$ecategory_sub)
# pcircos_3 <- pcircos_3 |> select(evarname, pvarname, estimate) |> complete(evarname, pvarname)
# estimate_wide_tbl <- pcircos_3 |> pivot_wider(names_from = pvarname, values_from = estimate) |> left_join(pcircos_2 |> select(evarname, ecategory_sub) |> unique())
# estimate_wide_matr <- estimate_wide_tbl |> select(-evarname, -ecategory_sub) |> as.matrix()
#
# exposome_domains <- factor(estimate_wide_tbl$ecategory_sub)
# col_fun1 = colorRamp2(c(-.1, 0, .1), c("blue", "white", "red"))
# circos.clear()
# circos.par(gap.degree = 5)
# circos.heatmap.initialize(estimate_wide_matr,split=exposome_domains)
# circos.heatmap(estimate_wide_matr[,1], col=col_fun1)
# circos.heatmap(estimate_wide_matr[,2], col=col_fun1)
# circos.heatmap(estimate_wide_matr[,3], col=col_fun1)
# circos.heatmap(estimate_wide_matr[,4], col=col_fun1)
# circos.heatmap(estimate_wide_matr[,5], col=col_fun1)
e_effect_sizes_per <- adjusted_meta_2 |> filter(sig_levels == 'Bonf.<0.05') |> group_by(ecategory, esubcategory, sign(estimate)) |> summarize(median_pvalue=median(p.value), number_signficant=n(), mean_estimate=mean((estimate))) |> arrange(-mean_estimate)
## `summarise()` has grouped output by 'ecategory', 'esubcategory'. You can
## override using the `.groups` argument.
e_effect_sizes_per <- e_effect_sizes_per |> mutate(esubcategory = ifelse(is.na(esubcategory), ecategory, esubcategory))
p <- ggplot(e_effect_sizes_per, aes(mean_estimate, -log10(median_pvalue), label=esubcategory))
p <- p + geom_point(aes(size=number_signficant)) + geom_text_repel() + geom_vline(xintercept = 0)
p <- p + theme_bw() + xlab("Average(Estimate) within exposome groups") + ylab("Median log10(pvalue)")
p <- p + theme(legend.position = "bottom")
p
## Warning: ggrepel: 14 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

p_effect_sizes_per <- adjusted_meta_2 |> filter(sig_levels == 'Bonf.<0.05') |> group_by(pcategory, psubcategory) |> summarize(mean_r2 = mean(mean_adjusted_base_r2_diff, na.rm=T))
## `summarise()` has grouped output by 'pcategory'. You can override using the
## `.groups` argument.
p <- ggplot(adjusted_meta_2 |> filter(vartype =='categorical'), aes(abs(estimate), color=sig_levels))
p <- p + stat_ecdf() + scale_x_continuous(limits=c(0, .25))
p <- p + xlab("abs(estimate)") + ylab("percentile") + theme(legend.position="bottom") + scale_color_npg()
p
## Warning: Removed 2210 rows containing non-finite values (stat_ecdf).

p <- ggplot(adjusted_meta_2 |> filter(vartype =='continuous'), aes(abs(estimate), color=sig_levels))
p <- p + stat_ecdf() + scale_x_continuous(limits=c(0, .25))
p <- p + xlab("abs(estimate)") + ylab("percentile") + theme(legend.position="bottom") + scale_color_npg()
p
## Warning: Removed 263 rows containing non-finite values (stat_ecdf).

p <- ggplot(adjusted_meta_2, aes(abs(estimate), color=sig_levels))
p <- p + stat_ecdf() + scale_x_continuous(limits=c(0, .25))
p <- p + xlab("abs(estimate)") + ylab("percentile") + theme(legend.position="bottom") + scale_color_npg()
p
## Warning: Removed 2479 rows containing non-finite values (stat_ecdf).

ecdf_for_sig <- adjusted_meta_2 |> filter(sig_levels == 'Bonf.<0.05') |> pull(mean_adjusted_base_r2_diff) |> ecdf()
ecdf_for_non_sig <- adjusted_meta_2 |> filter(sig_levels == '> BY & Bonf.') |> pull(mean_adjusted_base_r2_diff) |> ecdf()
p_effect_sizes_per <- p_effect_sizes_per |> mutate(q = ecdf_for_sig(mean_r2), sig_levels ='Bonf.<0.05')
p_effect_sizes_per <- p_effect_sizes_per |> mutate(p_cat = ifelse(is.na(psubcategory), pcategory, psubcategory))
p <- ggplot(adjusted_meta_2, aes(mean_adjusted_base_r2_diff, color=sig_levels))
p <- p + stat_ecdf() + scale_x_continuous(limits=c(0, .05)) +scale_color_aaas()
p <- p + geom_point(data=p_effect_sizes_per, aes(x=mean_r2, y = q, color=sig_levels))
p <- p + geom_text_repel(data=p_effect_sizes_per, aes(x=mean_r2, y = q, color=sig_levels, label=p_cat))
p <- p + xlab("R^2 (adjusted-base model)") + ylab("percentile")
p <- p + theme_bw() + theme(legend.position="bottom")
p
## Warning: Removed 1395 rows containing non-finite values (stat_ecdf).
## Warning: ggrepel: 4 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

Association sizes for all exposures
contextualizing all exposures
adjusted_meta_2 <- adjusted_meta_2 |> mutate(evarname = fct_reorder(evarname, abs(estimate), mean))
#p <- ggplot(adjusted_meta_2, aes(x=evarname, y=estimate, group=evarname))
#p <- p + geom_density_ridges()
#p <- p + geom_boxplot() + facet_grid(~sig_levels)
#p
Replicability and Consistency
I2 across number of surveys for P-E pair
## reorder sig_levels
adjusted_meta_2 <- adjusted_meta_2 |> mutate(sig_levels=fct_relevel(sig_levels, c("> BY & Bonf.","BY<0.05", "Bonf.<0.05")))
p <- ggplot(adjusted_meta_2, aes(factor(nobs), i.squared,color=sig_levels))
p <- p + geom_boxplot() + xlab("Number of Surveys for PE Association") + theme(legend.position="bottom") + scale_color_aaas()
p <- p + theme_bw() + theme(legend.position="bottom") + ylab("i-squared")
p

i2_medians <- adjusted_meta_2 |> group_by(sig_levels) |> summarize(i2_median=median(i.squared))
Showcasing associations:
- Low pvalue, Higher R2, low I2
- Low pvalue, Higher R2, and higher I2
adjusted_meta_3 |> filter(pvalue_bonferroni < 0.05) |> nrow()
## [1] 10602
adjusted_meta_3 |> filter(pvalue_bonferroni < 0.05, n_pvalue_lt >= 2) |> nrow()
## [1] 5048
non_het_pairs <- adjusted_meta_3 |> filter(pvalue_bonferroni < 0.05, n_pvalue_lt >= 2, i.squared < 50, mean_adjusted_base_r2_diff > .025)
het_pairs <- adjusted_meta_3 |> filter(pvalue_bonferroni < 0.05, n_pvalue_lt >= 2, i.squared > 50, mean_adjusted_base_r2_diff > .025, nobs >= 4)
#het_pairs_2 <- adjusted_meta_3 |> filter(sig_levels == 'BY<0.05', i.squared > 90, nobs >= 4)
adjusted_meta_3 |> filter(pvalue_bonferroni < 0.05) |> group_by(ecategory) |> count()
## # A tibble: 8 × 2
## # Groups: ecategory [8]
## ecategory n
## <chr> <int>
## 1 allergy 5
## 2 housing 40
## 3 income 10
## 4 infection 286
## 5 nutrients 6011
## 6 physical activity 740
## 7 pollutant 3236
## 8 smoking 274
## non-heterogeneous example
plot_pair <- function(evarname_str, pvarname_str, estimate_limits=c(0.01,.35)) {
test_1 <- expos_wide |> filter(evarname == evarname_str, pvarname == pvarname_str) |> select(Begin.Year, exposure_table_name, phenotype_table_name, e_variable_description, p_variable_description, estimate_adjusted, std.error_adjusted, p.value_adjusted)
exposure_name <- remove_units_from_string(test_1$e_variable_description[1])
phenotype_name <- remove_units_from_string(test_1$p_variable_description[1])
test_1 <- test_1 |> select(Begin.Year, estimate_adjusted, std.error_adjusted) |> rename(estimate=estimate_adjusted, std.error = std.error_adjusted, Survey=Begin.Year) |> mutate(i.squared = NA, i.squared_text='')
meta_test_1 <- adjusted_meta_2 |> filter(evarname == evarname_str, pvarname == pvarname_str) |> mutate(Survey = 'overall') |> select(Survey, estimate, std.error, i.squared) |> mutate(i.squared_text = sprintf("%i%%", round(i.squared)))
test_1 <- test_1 |> rbind(meta_test_1)
test_1 <- test_1 |> mutate(point_shape = ifelse(Survey == 'overall', 23, 21)) |> mutate(point_shape = as.integer(point_shape))
test_1 <- test_1 |> mutate(point_size = ifelse(Survey == 'overall', 7, 2))
p <- ggplot(test_1, aes(Survey, estimate))
p <- p + geom_point(aes(shape=point_shape, size=point_size, fill=point_shape)) + scale_shape_identity() + scale_size_identity()
p <- p + geom_text(data=meta_test_1, aes(Survey, estimate, label=i.squared_text), size=3, color="black", nudge_x=.6)
p <- p + geom_errorbar(aes(ymin=estimate-1.96*std.error, ymax=estimate+1.96*std.error), width=.1) + scale_x_discrete(limits=rev)
p <- p + scale_y_continuous(limits=estimate_limits)
p <- p + coord_flip() + theme_bw() + theme(legend.position = "none")
p <- p + ggtitle(sprintf('scale(%s)-scale(log10(%s))', phenotype_name, exposure_name))+ theme(plot.title = element_text(size = 7))
}
## non-heterogeneous example
p1 <- plot_pair('URXP01', 'LBDNENO')
## heterogeneous example
p2 <- plot_pair('LBXGTC', 'BMXBMI')
p3 <- plot_pair('LBXBPB', 'BMXHT', c()) # 33% i2
p4 <- plot_pair('LBXCOT', 'BPXPLS', c()) # 33% i2
#expos_wide |> filter(evarname == 'LBXPFOS', pvarname == 'LBXSAL')
plot_grid(p1, p2, p3, p4, ncol=2,labels = c('A', 'B', "C", "D"), label_size = 12)

# Examples for paper of top hits
rbind(
adjusted_meta_2 |> filter(evarname == 'LBXPFHS', pvarname == 'LBXSAL') |> select(tau.squared),
adjusted_meta_2 |> filter(evarname == 'LBXGTC', pvarname == 'LBXTC') |> select(tau.squared),
adjusted_meta_2 |> filter(evarname == 'LBXBPB', pvarname == 'BMXWT') |> select(tau.squared),
adjusted_meta_2 |> filter(evarname == 'LBXCOT', pvarname == 'LBDNENO') |> select(tau.squared)
)
## # A tibble: 4 × 1
## tau.squared
## <dbl>
## 1 0.0000737
## 2 0
## 3 0.0000634
## 4 0.00000143
adjusted_meta_2 |> filter(evarname == 'LBXPFHS') |> group_by(sig_levels) |> summarize(sd_estimate=sd(estimate))
## # A tibble: 3 × 2
## sig_levels sd_estimate
## <fct> <dbl>
## 1 > BY & Bonf. 0.0282
## 2 BY<0.05 0.0682
## 3 Bonf.<0.05 0.107
adjusted_meta_2 |> filter(evarname == 'LBXGTC') |> group_by(sig_levels) |> summarize(sd_estimate=sd(estimate))
## # A tibble: 3 × 2
## sig_levels sd_estimate
## <fct> <dbl>
## 1 > BY & Bonf. 0.0269
## 2 BY<0.05 0.0587
## 3 Bonf.<0.05 0.143
adjusted_meta_2 |> filter(evarname == 'LBXBPB') |> group_by(sig_levels) |> summarize(sd_estimate=sd(estimate))
## # A tibble: 3 × 2
## sig_levels sd_estimate
## <fct> <dbl>
## 1 > BY & Bonf. 0.0349
## 2 BY<0.05 0.0566
## 3 Bonf.<0.05 0.0858
adjusted_meta_2 |> filter(evarname == 'LBXCOT') |> group_by(sig_levels) |> summarize(sd_estimate=sd(estimate))
## # A tibble: 3 × 2
## sig_levels sd_estimate
## <fct> <dbl>
## 1 > BY & Bonf. 0.0268
## 2 BY<0.05 0.0441
## 3 Bonf.<0.05 0.0814
p1 <- plot_pair('LBXPFHS', 'LBXSAL') + ylab("Association Estimate")
## heterogeneous example
p2 <- plot_pair('LBXGTC', 'LBXTC') + ylab("Association Estimate")
p3 <- plot_pair('LBXBPB', 'BMXWT', c(-.3, 0)) + ylab("Association Estimate")
p4 <- plot_pair('LBXCOT', 'LBDNENO')+ ylab("Association Estimate")
plot_grid(p1, p2, p3, p4, ncol=2,labels = c('A', 'B', "C", "D"), label_size = 12)

library(ggridges)
## show histogram of associations for all top findings for LBXGTC, "LBXBPB", "LBXPFHS", "LBXCOT"
ep_candidates <- tibble(evarname = c("LBXGTC", "LBXBPB", "LBXPFHS", "LBXCOT"),
pvarname = c("LBXTC", "BMXWT", "LBXSAL", "LBDNENO"))
exposure_dist <- adjusted_meta_2 |> filter(evarname %in% ep_candidates$evarname) |> filter(sig_levels == "Bonf.<0.05") |> mutate(evardesc = remove_units_from_string(evardesc))
## collect Survey specific associations
survey_exposure_pts <- vector(mode = "list", length=nrow(ep_candidates))
for(rw_num in 1:nrow(ep_candidates)) {
survey_exposure_pts[[rw_num]] <- expos_wide |> filter(evarname == ep_candidates$evarname[rw_num], pvarname == ep_candidates$pvarname[rw_num]) |>
select(Begin.Year, evarname, pvarname, exposure_table_name, phenotype_table_name, e_variable_description, p_variable_description, estimate_adjusted, std.error_adjusted, p.value_adjusted)
}
survey_exposure_pts <- survey_exposure_pts |> bind_rows() |> mutate(evardesc=remove_units_from_string(e_variable_description))
exposure_dist <- exposure_dist |> mutate(evarname = substr(evarname, 4, 8))
survey_exposure_pts <- survey_exposure_pts |> mutate(pvarname = substr(pvarname, 4, 8), evarname = substr(evarname, 4, 8))
p <- ggplot(exposure_dist, aes(y=evarname, x=estimate, fill=evarname))
p <- p + geom_density_ridges()+ scale_fill_jama(guide="none") #+ scale_colour_continuous(guide = "none")
p <- p + geom_point(data=survey_exposure_pts, aes(y=evarname, x=estimate_adjusted, color=factor(Begin.Year))) + scale_color_aaas(name = "")
pheno_het <- p + theme_bw() + theme(legend.position='bottom') + ylab("Exposure Name") + xlab("Association Estimate")
survey_het <- plot_grid(p1, p2, p3, p4, ncol=2,labels = c('A', 'B', "C", "D"), label_size = 12)
p <- plot_grid(survey_het, pheno_het, ncol=2, labels=c("", "E"), label_size = 12)
## Picking joint bandwidth of 0.0395
p <- ggplot(adjusted_meta_2 , aes(estimate, estimate_unadjusted, color=sig_levels)) ## have to get this
p <- p + geom_point(shape='.') + scale_x_continuous(limits=c(-1, 1)) + scale_y_continuous(limits=c(-1, 1)) + scale_color_aaas()
p <- p + geom_abline()
p <- p + facet_grid(~sig_levels) + xlab("Adjusted model estimate [Exposure + Demographics]") + ylab("Unadjusted estimate [Exposure]")
p <- p + geom_smooth(method="lm")
p <- p + theme_bw() +theme(legend.position = "none")
p
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 193 rows containing non-finite values (stat_smooth).
## Warning: Removed 193 rows containing missing values (geom_point).

#
#
#
tidy(lm(estimate ~ estimate_unadjusted, adjusted_meta_2))
## # A tibble: 2 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -0.00471 0.000177 -26.6 1.27e-155
## 2 estimate_unadjusted 0.464 0.00141 329. 0
tidy(lm(estimate ~ estimate_unadjusted, adjusted_meta_2 |> filter(pvalue_bonferroni < .05)))
## # A tibble: 2 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -0.0153 0.000877 -17.4 6.27e-67
## 2 estimate_unadjusted 0.631 0.00476 133. 0
tidy(lm(estimate ~ estimate_unadjusted, adjusted_meta_2 |> filter(sig_levels == '> BY & Bonf.')))
## # A tibble: 2 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -0.00350 0.000180 -19.5 2.26e-84
## 2 estimate_unadjusted 0.421 0.00155 272. 0
tidy(lm(estimate ~ estimate_unadjusted, adjusted_meta_2 |> filter(sig_levels == 'BY<0.05')))
## # A tibble: 2 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -0.00639 0.000632 -10.1 6.38e-24
## 2 estimate_unadjusted 0.485 0.00460 105. 0
#
p <- ggplot(adjusted_meta_2 , aes(estimate_unadjusted, estimate, color=ecategory))
p <- p + geom_point(shape='.') + scale_x_continuous(limits=c(-1, 1)) + scale_y_continuous(limits=c(-1, 1)) + scale_color_aaas()
p <- p + geom_abline()
p <- p + facet_grid(~ecategory) + ylab("Adjusted model estimate [Exposure + Demographics]") + xlab("Unadjusted estimate [Exposure]")
p <- p + geom_smooth(method="lm")
p <- p + theme_bw() +theme(legend.position = "none")
p
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 193 rows containing non-finite values (stat_smooth).
## Removed 193 rows containing missing values (geom_point).

Which e and P domains are most subject to demographic bias?
bias_per_ecategory <- adjusted_meta_2 |> group_by(ecategory) |> summarize(
mod=list(lm(estimate ~ estimate_unadjusted))) |> mutate(tidied=map(mod, tidy)) |> unnest(tidied)
bias_per_ecategory |> select(-mod) |> select(ecategory, term, estimate, p.value) |> filter(term == "estimate_unadjusted") |> select(-term)
## # A tibble: 9 × 3
## ecategory estimate p.value
## <chr> <dbl> <dbl>
## 1 allergy 0.753 2.65e-94
## 2 autoantibody 0.478 3.09e-64
## 3 housing 0.354 4.72e-81
## 4 income 0.725 0
## 5 infection 0.557 0
## 6 nutrients 0.287 0
## 7 physical activity 0.415 0
## 8 pollutant 0.386 0
## 9 smoking 0.660 0
bias_per_pcategory <- adjusted_meta_2 |> group_by(pcategory) |> summarize(
mod=list(lm(estimate ~ estimate_unadjusted))) |> mutate(tidied=map(mod, tidy)) |> unnest(tidied)
bias_per_pcategory |> select(-mod) |> select(pcategory, term, estimate, p.value) |> filter(term == "estimate_unadjusted") |> select(-term)
## # A tibble: 8 × 3
## pcategory estimate p.value
## <chr> <dbl> <dbl>
## 1 aging 0.300 9.28e- 16
## 2 anthropometric 0.347 0
## 3 biochemistry 0.665 0
## 4 blood 0.675 0
## 5 blood pressure 0.514 0
## 6 fitness 0.637 3.56e-159
## 7 lung 0.379 8.71e-193
## 8 microbiome 0.791 0
Multivariate R2 of the exposome
p <- ggplot(mvr2, aes(n_evars, mv*100))
p <- p + geom_point() + theme_bw()
p <- p + geom_text_repel(data=mvr2 |> filter(mv > .1),aes(n_evars, mv*100, label=substr(pvarname, 4, 10) ), max.overlaps = 20)
p <- p + xlab("Number of Exposome Variables in Model") + ylab("R-squared (%)")
p1 <- p
p <- ggplot(mvr2, aes(base_adj_rsq, mve_rsq))
p <- p + geom_point() + theme_bw()
p <- p + geom_text_repel(data=mvr2 |> filter(mv > .1),aes(base_adj_rsq, mve_rsq, label=substr(pvarname, 4, 10) ), max.overlaps = 20)
p <- p + xlab("R2 (Demographic Model)") + ylab("R2 (Full Model)")
p2 <- p
p3 <- ggplot(mvr2, aes(n_evars, mve_rsq))
p3 <- p3 + geom_point(aes(n_evars, base_adj_rsq))
p3 <- p3 + geom_segment(aes(x=n_evars, y=base_adj_rsq, xend=n_evars, yend=mve_rsq),arrow = arrow(length = unit(0.01, "npc")))
p3 <- p3 + geom_text_repel(data=mvr2 |> filter(mv > .1), aes(n_evars, mve_rsq, label=substr(pvarname, 4, 10) ), max.overlaps = 20)
p3 <- p3 + theme_bw()
p3

mvr2 |> summarize(mean_sample_size=mean(n), median_r2=median(mv), q25_r2=quantile(mv, probs=.25), q75_r2=quantile(mv, probs=.75))
## # A tibble: 1 × 4
## mean_sample_size median_r2 q25_r2 q75_r2
## <dbl> <dbl> <dbl> <dbl>
## 1 16621. 0.0153 0.00458 0.0365
mvr2 |> summarize(n_min=min(n), n_max=max(n), n_evars_min=min(n_evars), n_evars_max=max(n_evars))
## # A tibble: 1 × 4
## n_min n_max n_evars_min n_evars_max
## <int> <int> <int> <int>
## 1 1602 68340 0 86
mvr2 |> arrange(-n_evars) |> filter(mv > .1) |> mutate(pvarname=substr(pvarname, 4, 8)) |> select(pvarname, pvardesc) |> unite("index", pvarname, pvardesc, sep=":") |> print(n=26)
## # A tibble: 16 × 1
## index
## <chr>
## 1 TRPF:Trunk Percent Fat
## 2 RBF:Folate, RBC (ng/mL RBC)
## 3 SF1SI:5-Methyl-tetrahydrofolate (nmol/L)
## 4 FOT:Serum total folate (ng/mL)
## 5 RFO:RBC folate (ng/mL)
## 6 SATA:Subcutaneous fat area
## 7 SATM:Subcutaneous fat mass
## 8 SATV:Subcutaneous fat volume
## 9 TATA:Total abdominal fat area
## 10 TATM:Total abdominal fat mass
## 11 TATV:Total abdominal fat volume
## 12 FOL:Folate, serum (ng/mL)
## 13 STFAT:Subtotal Fat (g)
## 14 TOFAT:Total Fat (g)
## 15 TRFAT:Trunk Fat (grams)
## 16 THICR:Thigh Circumference (cm)
p <- plot_grid(p1, p2, ncol=2, labels=c("A", "B"))
Correlation of phenotypes in exposome space
library(corrr)
library(gplots)
##
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
##
## lowess
to_array <- adjusted_meta_2 |> filter(expo_name == 'expo', vartype == 'continuous') |> select(evarname, pvarname, estimate, p.value) |> mutate(estimate= ifelse(p.value >= 0.05, 0, estimate)) |> mutate(estimate = ifelse(is.na(estimate), 0, estimate)) |> select(-p.value) |> pivot_wider(names_from = pvarname, values_from = estimate)
exposure_correlation <- to_array |> select(-evarname) |> correlate(diagonal = 1)
## Warning in stats::cor(x = x, y = y, use = use, method = method): the standard
## deviation is zero
## Correlation computed with
## • Method: 'pearson'
## • Missing treated using: 'pairwise.complete.obs'
m <- exposure_correlation |> as_matrix()
m[is.na(m)] <- 0
heatmapColors <- function(numColors=16) {
c1 <- rainbow(numColors,v=seq(0.5,1,length=numColors),s=seq(1,0.3,length=numColors),start=4/6,end=4.0001/6);
c2 <- rainbow(numColors,v=seq(0.5,1,length=numColors),s=seq(1,0.3,length=numColors),start=1/6,end=1.0001/6);
c3 <- c(c1,rev(c2));
return(c3)
}
heatmap.2(m, trace = 'none', na.rm = F, scale = 'none', symm = T, col=heatmapColors(5), margins=c(16,16), sepwidth=c(.1, .1), symbreaks=T)

Correlation of the exposome
to_array <- adjusted_meta_2 |> filter(expo_name == 'expo', vartype == 'continuous') |> select(evarname, pvarname, estimate, p.value) |> mutate(estimate= ifelse(p.value >= 0.05, 0, estimate)) |> mutate(estimate = ifelse(is.na(estimate), 0, estimate)) |> select(-p.value) |> pivot_wider(names_from = evarname, values_from = estimate)
phenome_correlation <- to_array |> select(-pvarname) |> correlate(diagonal = 1)
## Warning in stats::cor(x = x, y = y, use = use, method = method): the standard
## deviation is zero
## Correlation computed with
## • Method: 'pearson'
## • Missing treated using: 'pairwise.complete.obs'
m <- phenome_correlation |> as_matrix()
m[is.na(m)] <- 0
heatmap.2(m, trace = 'none', na.rm = F, scale = 'none', symm = T, col=heatmapColors(5), margins=c(16,16), sepwidth=c(.1, .1), symbreaks=T)
